Meng Yang

Electrohydraulic actuators (EHAs) are critical in applications demanding compact designs, high power density, and precise motion control. However, their nonlinear dynamics and inherent uncertainties pose considerable control challenges. This study develops a reinforcement learning (RL)-based control framework, integrating an actor–critic algorithm [deep deterministic policy gradient (DDPG)] and a novel reward-shaping method to address these challenges without requiring prior expert knowledge. The proposed approach is validated on a heavy-duty EHA-driven inverted pendulum testbench, as a benchmark system for nonlinear and unstable dynamics. Experimental results demonstrate the RL controller’s effectiveness in achieving the dual-control goal: swing-up and balancing of the EHA-driven pendulum. Furthermore, a comparative analysis with the classical linear quadratic regulator (LQR) highlights the strengths and limitations between RL-based control and model-based control. This study serves as fundamental research, offering practical and theoretical contributions to the application of RL in advanced motion control for EHAs and other complex systems.

The hydraulic joint is the key driving component of a robot. To reduce the joint size of the hydraulic robot, and improve the control accuracy and dynamic response performance, this paper proposes a novel joint structure and control method of a ball double-screw hydraulic robot. Using ball and circular arc spiral groove transmission, the hydraulic joint has a small transmission friction coefficient, compact overall structure and higher transmission accuracy. Aiming to resolve the problems of low control accuracy and motion instability caused by temperature drift in valve-controlled hydraulic systems, the high-precision joint control method based on adaptive fuzzy control compensation is used to improve the control accuracy and stability. The static and dynamic characteristics of the designed hydraulic joint are analyzed by simulation. A test platform was built, and the physical prototype of the hydraulic joint underwent static testing, dynamic control, amplitude frequency response and trajectory tracking tests. The experimental results were similar to the simulation results. The ball double-screw hydraulic robot joint has the characteristics of low starting pressure, high energy density, fast dynamic response, small amplitude frequency attenuation and high control accuracy. The starting pressure is 0.5 MPa, maximum swing frequency is 3 Hz, positioning accuracy is ± 0.03°, tracking accuracy is ± 3.9° and maximum angular velocity at 10 MPa is about 7.6 rad/s, which is close to the angular velocity of the actual human joint.

In this research, we studied the impact of temperature dependent viscosity and thermal radiation on Eyring Powell fluid with porous channels. The dimensionless equations were solved using the perturbation technique using the Weissenberg number (ε ≪ 1) to obtain clear formulas for the velocity field. All of the solutions for the physical parameters of the Reynolds number (Re), magnetic parameter (M), Darcy parameter (Da) and Prandtl number (Pr) were discussed through their different values. As shown in the plots the two-dimensional and three-dimensional graphical results of the velocity profile against various pertinent parameters have been illustrated with physical reasons. The results revealed that the temperature distribution increases for higher Prandtl and thermal radiation values. Such findings are beneficial in the field of engineering sciences.

Oil shortages and environmental pollution are attracting worldwide attention incrementally. Hybrid falls within one of the effective techniques for those two problems. Taking the loader with high energy consumption and high emission as the target, combined with the hydraulic hybrid technology with high power density and strong energy storage capacity, the parallel hydraulic hybrid loader (PHHL) based on brake energy regeneration is proposed. Firstly, the dynamic models of the key components of the PHHL are established, and the parameters of the part which coincides with the ordinary loader are corrected based on the V-type duty cycle. Then, consid-ering the energy recovery efficiency as well as the characteristics of the loader from the V-type duty cycle, the parameters for several major parts of the energy regeneration system (ERS) were calculated and matched. Then, based on the initial matching, the improved adaptive genetic al-gorithm (AGA) is employed to optimize the control variable of the control strategy and the design parameters of ERS to enhance the economic benefit and performance of the ERS. Furthermore, a simulation validation was conducted. Simulation results show that the ERS with optimized pa-rameters could improve the fuel-saving effect by 25% compared to the ERS with initial parameters, which indicated the rationality of the optimized parameters. Finally, the fuel consumption test of the PHHL prototype under the V-type duty cycle is performed. The results show that the PHHL with the optimization scheme can achieve 9.12% fuel saving, which is on the brink of the potential of brake energy recovery and verifies the feasibility of applying hydraulic hybrid technology on the loader.

For the purpose of reducing unrecoverable economic losses and casualties all over the world, automatic fire detection is expected to recognize fire and give an alarm as early as possible. Due to the disadvantages of traditional methods, fire image detection has become an attractive solution. This paper pro-poses an innovative approach, based on multi-feature vector and support vector machine coupling with improved particle swarm optimization (IPSO-SVM). Firstly, a multi-feature vector is established, including geometric, texture, spectrum information. Then, an improved particle swarm optimization (IPSO) is developed by introducing dynamic inertia weight factor and cross-variation. Next, an IPSO-SVM model is established to achieve the fire image detection, where the IPSO algorithm is imported to select the optimal parameters of support vector machine (SVM). Afterwards, the detection performance of presented method is verified by a series of case studies. Eventually, the results indicate that the provided method has an advantage over other benchmark algorithms, obtaining the highest rate of 98.33, and proving its effectiveness and feasibility.

Unmanned road roller has become an attractive solution to reduce operators’ working intensity and improve compaction efficiency. As a result of working in bumpy environments, sideslip effect is unavoidable during the compacting process. In order to guarantee the reliability and stability of path tracking control, a novel and effective method based on preview control and sideslip compensation is proposed in this paper. The kinematic and dynamic models of articulated road roller considering sideslip angles are obtained first. Then, a preview controller with sideslip compensation (PCSC) is developed to eliminate the path tracking errors between the actual path and the desired path. To evaluate the control performance of the proposed method, simulation under the MATLAB/Simulink and automatic compaction experiments at the construction site were performed with initial errors. Finally, the simulation and experimental results show that the path tracking errors can converge to zero as time goes by. The proposed method has the ability to navigate an articulated road roller to track a desired path in the existence of sideslip, only regarding the steering angle dynamic as control input. Compared with other benchmark method, it not only improves the control accuracy, but also increases the convergence rate, proving its effectiveness and feasibility. All these also demonstrate the practical value and validity of the proposed models with sideslip.

Accurate combustion state recognition of flame images not only plays an important role in social security, but also contributes to increasing thermal efficiency and product quality. To improve the accuracy of feature extraction and achieve the combustion state recognition, a novel method based on radial Chebyshev moment invariants (RCMIs) and an improved firefly algorithm-wavelet support vector machine (IFA-WSVM) model is proposed. Firstly, the potential flame pixels and the potential flame contour are obtained in the pre-processing phase. Then, the rotation, translation and scaling (RTS) invariants of radial Chebyshev moments are derived. Combing the region and contour moments, the RCMIs of pre-processed and edge images are calculated to construct multi-feature vectors. To enhance the recognition performance, an IFA-WSVM model is built, where the IFA is applied to search the best parameters of WSVM. Then, the IFA-WSVM model is used to recognize the combustion state. Finally, the result for case studies show that the proposed method is superior to methods based on HMIs and ZMIs, achieving the highest rate of 99.07% in real time. The IFA algorithm also outperforms other benchmark algorithms. Even for the images transformed by RTS and small size of training sets, the proposed method continues to exhibit the best performance.